Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 10971
    Prev
    Next
    INDEX
    Explanations

    quoted strings or documentation comments in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <b>
    -0.74
    a
    -0.70
    </b>
    -0.69
     ± 
    -0.66
    ed
    -0.64
    Хро
    -0.64
    clé
    -0.64
     McCra
    -0.64
     Kristina
    -0.64
     blue
    -0.63
    POSITIVE LOGITS
    """
    1.88
     """
    1.69
    ."""
    1.64
    """
    
    1.36
    ("""
    1.22
     ***!
    1.19
    """"
    1.13
     """
    
    1.09
     MonoBehaviour
    1.07
    '''
    1.07
    Activations Density 0.132%

    No Known Activations